量化投資與Python——pandas

簡介：

案例

# -*- coding: utf-8 -*-

# @File    : pandas-基礎.py
# @Date    : 2020-06-09
# @Author  : Administrator

import pandas as pd
import dateutil
from datetime import datetime

# ################ Series ################
a = pd.Series([4, 5, 6, 3])
# print(a)
# 0    4
# 1    5
 

# 2    6
# 3    3
# dtype: int64

b = pd.Series([4, 5, 6, 3], index=['a', 'b', 'c', 'd'])
print(b)

# a    4
# b    5
# c    6
# d    3
# dtype: int64


# 既可以通過下標訪問，也可以通過 key 來訪問
# print(b[2],b['c'])  # 6 6


# 按照標籤進行累加
c = pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])
d = pd.Series([1, 2, 3, 4], index=['
 
b', 'c', 'a', 'd'])
print(c+d)
# a    4
# b    3
# c    5
# d    8
# dtype: int64


# 如果兩個列表的標籤不一致，則只累加標籤一致的結果，其它為空
e = pd.Series([1, 2, 3, 4], index=['b', 'b', 'a', 'd'])
print(e+c)
# a    4.0
# b    3.0
# b    4.0
# c    NaN
# d    8.0
# dtype: float64


# ################ Series ################
f = pd.DataFrame({'
 
one': [1, 2, 3], 'two': [4, 5, 6]})
print(f)

#    one  two
# 0    1    4
# 1    2    5
# 2    3    6

g = pd.DataFrame({'one': [1, 2, 3], 'two': [4, 5, 6]}, index=['a', 'b', 'c'])
print(g)

#    one  two
# a    1    4
# b    2    5
# c    3    6

h = pd.DataFrame({'one': pd.Series([1, 2, 3], index=['a', 'b', 'c']),'two': pd.Series([1, 2, 3, 4], index=['a', 'b', 'c', 'd'])})
print(h)
#    one  two
# a  1.0    1
# b  2.0    2
# c  3.0    3
# d  NaN    4

print(h.keys())     # Index(['one', 'two'], dtype='object')
print(h.values)
# [[ 1.  1.]
#  [ 2.  2.]
#  [ 3.  3.]
#  [nan  4.]]

print(h.T)
#        a    b    c    d
# one  1.0  2.0  3.0  NaN
# two  1.0  2.0  3.0  4.0

print(h.describe())
#        one       two
# count  3.0  4.000000
# mean   2.0  2.500000
# std    1.0  1.290994
# min    1.0  1.000000
# 25%    1.5  1.750000
# 50%    2.0  2.500000
# 75%    2.5  3.250000
# max    3.0  4.000000

# 時間處理
now = datetime.now()
time = dateutil.parser.parser('2001-01-01')
print(time)     # <dateutil.parser._parser.parser object at 0x0000025D7A7A05C0>
pd_time = pd.to_datetime([now])
print(pd_time)  # DatetimeIndex(['2020-06-28 13:43:48.554969'], dtype='datetime64[ns]', freq=None)


# 批量生成時間佇列
time_list = pd.date_range('2020-01-01',periods=30,freq='W-MON')
print(time_list)

# DatetimeIndex(['2020-01-06', '2020-01-13', '2020-01-20', '2020-01-27',
#                '2020-02-03', '2020-02-10', '2020-02-17', '2020-02-24',
#                '2020-03-02', '2020-03-09', '2020-03-16', '2020-03-23',
#                '2020-03-30', '2020-04-06', '2020-04-13', '2020-04-20',
#                '2020-04-27', '2020-05-04', '2020-05-11', '2020-05-18',
#                '2020-05-25', '2020-06-01', '2020-06-08', '2020-06-15',
#                '2020-06-22', '2020-06-29', '2020-07-06', '2020-07-13',
#                '2020-07-20', '2020-07-27'],
#               dtype='datetime64[ns]', freq='W-MON')

Series

DataFrame